ASAP_FineTuningBERT_noAug_task1_organization_fold1

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4110
• Qwk: 0.7053
• Mse: 0.4110
• Rmse: 0.6411

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0149	2	9.6673	0.0	9.6673	3.1092
No log	0.0299	4	8.2915	0.0152	8.2915	2.8795
No log	0.0448	6	6.7749	0.0019	6.7749	2.6029
No log	0.0597	8	5.1933	-0.0002	5.1933	2.2789
No log	0.0746	10	3.8351	0.0110	3.8351	1.9583
No log	0.0896	12	2.7953	0.0123	2.7953	1.6719
No log	0.1045	14	2.1088	0.0	2.1088	1.4522
No log	0.1194	16	1.6576	0.0	1.6576	1.2875
No log	0.1343	18	1.2642	0.1780	1.2642	1.1244
No log	0.1493	20	1.0911	0.0568	1.0911	1.0445
No log	0.1642	22	0.9408	0.0106	0.9408	0.9700
No log	0.1791	24	0.8680	0.0	0.8680	0.9317
No log	0.1940	26	0.8533	0.0	0.8533	0.9237
No log	0.2090	28	0.8680	0.0769	0.8680	0.9316
No log	0.2239	30	0.9492	0.3677	0.9492	0.9743
No log	0.2388	32	0.8094	0.3940	0.8094	0.8997
No log	0.2537	34	0.6752	0.1435	0.6752	0.8217
No log	0.2687	36	1.1405	0.1871	1.1405	1.0679
No log	0.2836	38	0.8802	0.2208	0.8802	0.9382
No log	0.2985	40	0.6035	0.4604	0.6035	0.7769
No log	0.3134	42	0.9252	0.3881	0.9252	0.9619
No log	0.3284	44	0.9330	0.3548	0.9330	0.9659
No log	0.3433	46	0.6931	0.4832	0.6931	0.8325
No log	0.3582	48	0.5320	0.4662	0.5320	0.7294
No log	0.3731	50	0.5101	0.4412	0.5101	0.7142
No log	0.3881	52	0.6240	0.3112	0.6240	0.7899
No log	0.4030	54	0.5195	0.4066	0.5195	0.7207
No log	0.4179	56	0.5851	0.5517	0.5851	0.7649
No log	0.4328	58	0.7843	0.5155	0.7843	0.8856
No log	0.4478	60	0.7154	0.5230	0.7154	0.8458
No log	0.4627	62	0.5064	0.5509	0.5064	0.7116
No log	0.4776	64	0.4766	0.4830	0.4766	0.6904
No log	0.4925	66	0.5339	0.3993	0.5339	0.7307
No log	0.5075	68	0.4626	0.5077	0.4626	0.6801
No log	0.5224	70	0.4733	0.5739	0.4733	0.6880
No log	0.5373	72	0.4456	0.5641	0.4456	0.6675
No log	0.5522	74	0.5092	0.4611	0.5092	0.7136
No log	0.5672	76	0.6152	0.3750	0.6152	0.7843
No log	0.5821	78	0.4511	0.5355	0.4511	0.6717
No log	0.5970	80	0.5300	0.5823	0.5300	0.7280
No log	0.6119	82	0.9148	0.4758	0.9148	0.9565
No log	0.6269	84	0.9075	0.4691	0.9075	0.9526
No log	0.6418	86	0.6294	0.5564	0.6294	0.7933
No log	0.6567	88	0.5152	0.3912	0.5152	0.7178
No log	0.6716	90	0.6939	0.2999	0.6939	0.8330
No log	0.6866	92	0.5894	0.3166	0.5894	0.7678
No log	0.7015	94	0.4877	0.5258	0.4877	0.6984
No log	0.7164	96	0.7301	0.5164	0.7301	0.8545
No log	0.7313	98	0.9480	0.4004	0.9480	0.9736
No log	0.7463	100	0.9024	0.4180	0.9024	0.9500
No log	0.7612	102	0.6434	0.5640	0.6434	0.8021
No log	0.7761	104	0.5070	0.4119	0.5070	0.7120
No log	0.7910	106	0.6659	0.2676	0.6659	0.8160
No log	0.8060	108	0.8403	0.2739	0.8403	0.9167
No log	0.8209	110	0.7080	0.2820	0.7080	0.8414
No log	0.8358	112	0.4740	0.4394	0.4740	0.6885
No log	0.8507	114	0.4505	0.5628	0.4505	0.6712
No log	0.8657	116	0.4906	0.6017	0.4906	0.7004
No log	0.8806	118	0.4564	0.6050	0.4564	0.6756
No log	0.8955	120	0.4317	0.6227	0.4317	0.6570
No log	0.9104	122	0.4076	0.6194	0.4076	0.6385
No log	0.9254	124	0.4106	0.5758	0.4106	0.6408
No log	0.9403	126	0.4393	0.5755	0.4393	0.6628
No log	0.9552	128	0.4063	0.6023	0.4063	0.6374
No log	0.9701	130	0.4333	0.6376	0.4333	0.6582
No log	0.9851	132	0.4361	0.6199	0.4361	0.6604
No log	1.0	134	0.4395	0.6244	0.4395	0.6629
No log	1.0149	136	0.5318	0.6363	0.5318	0.7292
No log	1.0299	138	0.5356	0.6395	0.5356	0.7319
No log	1.0448	140	0.4219	0.6272	0.4219	0.6495
No log	1.0597	142	0.4490	0.5448	0.4490	0.6700
No log	1.0746	144	0.4485	0.5374	0.4485	0.6697
No log	1.0896	146	0.3999	0.5933	0.3999	0.6324
No log	1.1045	148	0.5310	0.6694	0.5310	0.7287
No log	1.1194	150	0.5782	0.5965	0.5782	0.7604
No log	1.1343	152	0.4435	0.6179	0.4435	0.6659
No log	1.1493	154	0.4067	0.5788	0.4067	0.6377
No log	1.1642	156	0.4944	0.5036	0.4944	0.7032
No log	1.1791	158	0.5225	0.4872	0.5225	0.7228
No log	1.1940	160	0.4267	0.5502	0.4267	0.6532
No log	1.2090	162	0.4229	0.6037	0.4229	0.6503
No log	1.2239	164	0.6407	0.6177	0.6407	0.8004
No log	1.2388	166	0.7832	0.6797	0.7832	0.8850
No log	1.2537	168	0.5729	0.6327	0.5729	0.7569
No log	1.2687	170	0.4706	0.6342	0.4706	0.6860
No log	1.2836	172	0.4741	0.6319	0.4741	0.6886
No log	1.2985	174	0.5484	0.6031	0.5484	0.7405
No log	1.3134	176	0.5063	0.6168	0.5063	0.7115
No log	1.3284	178	0.4268	0.6357	0.4268	0.6533
No log	1.3433	180	0.4418	0.7011	0.4418	0.6647
No log	1.3582	182	0.5272	0.6956	0.5272	0.7261
No log	1.3731	184	0.5128	0.6183	0.5128	0.7161
No log	1.3881	186	0.4121	0.6367	0.4121	0.6419
No log	1.4030	188	0.4393	0.5914	0.4393	0.6628
No log	1.4179	190	0.4722	0.4998	0.4722	0.6872
No log	1.4328	192	0.4620	0.5516	0.4620	0.6797
No log	1.4478	194	0.4884	0.6025	0.4884	0.6989
No log	1.4627	196	0.4582	0.6115	0.4582	0.6769
No log	1.4776	198	0.4404	0.6096	0.4404	0.6636
No log	1.4925	200	0.3885	0.5911	0.3885	0.6233
No log	1.5075	202	0.3844	0.5478	0.3844	0.6200
No log	1.5224	204	0.3915	0.5272	0.3915	0.6257
No log	1.5373	206	0.3759	0.5942	0.3759	0.6131
No log	1.5522	208	0.5195	0.6315	0.5195	0.7208
No log	1.5672	210	0.6342	0.5791	0.6342	0.7964
No log	1.5821	212	0.5630	0.6011	0.5630	0.7503
No log	1.5970	214	0.4732	0.6022	0.4732	0.6879
No log	1.6119	216	0.3933	0.6164	0.3933	0.6271
No log	1.6269	218	0.3833	0.5594	0.3833	0.6191
No log	1.6418	220	0.3783	0.5737	0.3783	0.6151
No log	1.6567	222	0.3738	0.5821	0.3738	0.6114
No log	1.6716	224	0.3777	0.6234	0.3777	0.6145
No log	1.6866	226	0.4346	0.6618	0.4346	0.6592
No log	1.7015	228	0.4812	0.6883	0.4812	0.6937
No log	1.7164	230	0.4978	0.6979	0.4978	0.7055
No log	1.7313	232	0.4036	0.6758	0.4036	0.6353
No log	1.7463	234	0.3841	0.6145	0.3841	0.6198
No log	1.7612	236	0.3860	0.6314	0.3860	0.6213
No log	1.7761	238	0.3809	0.6163	0.3809	0.6172
No log	1.7910	240	0.3804	0.5972	0.3804	0.6168
No log	1.8060	242	0.3807	0.6432	0.3807	0.6170
No log	1.8209	244	0.4307	0.6895	0.4307	0.6563
No log	1.8358	246	0.3976	0.6192	0.3976	0.6306
No log	1.8507	248	0.4072	0.5312	0.4072	0.6381
No log	1.8657	250	0.4003	0.5290	0.4003	0.6327
No log	1.8806	252	0.4424	0.6470	0.4424	0.6651
No log	1.8955	254	0.5031	0.6349	0.5031	0.7093
No log	1.9104	256	0.4471	0.6292	0.4471	0.6686
No log	1.9254	258	0.4276	0.6183	0.4276	0.6539
No log	1.9403	260	0.4228	0.6284	0.4228	0.6502
No log	1.9552	262	0.4118	0.6357	0.4118	0.6417
No log	1.9701	264	0.3963	0.6276	0.3963	0.6295
No log	1.9851	266	0.3928	0.6037	0.3928	0.6267
No log	2.0	268	0.4609	0.5279	0.4609	0.6789
No log	2.0149	270	0.4459	0.5564	0.4459	0.6678
No log	2.0299	272	0.4194	0.6890	0.4194	0.6476
No log	2.0448	274	0.4608	0.7074	0.4608	0.6788
No log	2.0597	276	0.4187	0.6986	0.4187	0.6471
No log	2.0746	278	0.3845	0.5839	0.3845	0.6201
No log	2.0896	280	0.4291	0.5466	0.4291	0.6550
No log	2.1045	282	0.3866	0.5815	0.3866	0.6218
No log	2.1194	284	0.4254	0.7118	0.4254	0.6522
No log	2.1343	286	0.5790	0.7540	0.5790	0.7609
No log	2.1493	288	0.4913	0.7269	0.4913	0.7009
No log	2.1642	290	0.3665	0.6680	0.3665	0.6054
No log	2.1791	292	0.3605	0.6344	0.3605	0.6004
No log	2.1940	294	0.3593	0.6495	0.3593	0.5994
No log	2.2090	296	0.3714	0.6787	0.3714	0.6094
No log	2.2239	298	0.4699	0.7101	0.4699	0.6855
No log	2.2388	300	0.5714	0.7495	0.5714	0.7559
No log	2.2537	302	0.4420	0.7054	0.4420	0.6648
No log	2.2687	304	0.3536	0.6379	0.3536	0.5946
No log	2.2836	306	0.3526	0.6309	0.3526	0.5938
No log	2.2985	308	0.3530	0.6300	0.3530	0.5942
No log	2.3134	310	0.4007	0.6909	0.4007	0.6330
No log	2.3284	312	0.6306	0.7703	0.6306	0.7941
No log	2.3433	314	0.6167	0.7733	0.6167	0.7853
No log	2.3582	316	0.4109	0.6874	0.4109	0.6410
No log	2.3731	318	0.3760	0.5771	0.3760	0.6131
No log	2.3881	320	0.4521	0.5130	0.4521	0.6724
No log	2.4030	322	0.4009	0.5375	0.4009	0.6332
No log	2.4179	324	0.3662	0.6514	0.3662	0.6051
No log	2.4328	326	0.4419	0.6991	0.4419	0.6648
No log	2.4478	328	0.4619	0.6961	0.4619	0.6796
No log	2.4627	330	0.5277	0.7092	0.5277	0.7264
No log	2.4776	332	0.4656	0.7045	0.4656	0.6823
No log	2.4925	334	0.4035	0.6701	0.4035	0.6352
No log	2.5075	336	0.3678	0.5933	0.3678	0.6065
No log	2.5224	338	0.3768	0.5488	0.3768	0.6138
No log	2.5373	340	0.3720	0.5577	0.3720	0.6099
No log	2.5522	342	0.3697	0.6139	0.3697	0.6080
No log	2.5672	344	0.4211	0.6798	0.4211	0.6489
No log	2.5821	346	0.4583	0.6917	0.4583	0.6770
No log	2.5970	348	0.4594	0.6946	0.4594	0.6778
No log	2.6119	350	0.3890	0.6588	0.3890	0.6237
No log	2.6269	352	0.3748	0.5595	0.3748	0.6122
No log	2.6418	354	0.3871	0.5340	0.3871	0.6222
No log	2.6567	356	0.3747	0.5588	0.3747	0.6122
No log	2.6716	358	0.3946	0.6269	0.3946	0.6282
No log	2.6866	360	0.5117	0.6851	0.5117	0.7154
No log	2.7015	362	0.5528	0.6816	0.5528	0.7435
No log	2.7164	364	0.4736	0.6508	0.4736	0.6882
No log	2.7313	366	0.4116	0.6420	0.4116	0.6415
No log	2.7463	368	0.4045	0.6370	0.4045	0.6360
No log	2.7612	370	0.4350	0.6881	0.4350	0.6595
No log	2.7761	372	0.4241	0.6798	0.4241	0.6512
No log	2.7910	374	0.4390	0.6986	0.4390	0.6626
No log	2.8060	376	0.4623	0.7127	0.4623	0.6799
No log	2.8209	378	0.4438	0.6979	0.4438	0.6662
No log	2.8358	380	0.4610	0.7061	0.4610	0.6789
No log	2.8507	382	0.4812	0.7010	0.4812	0.6937
No log	2.8657	384	0.4257	0.6435	0.4257	0.6524
No log	2.8806	386	0.4721	0.5524	0.4721	0.6871
No log	2.8955	388	0.4406	0.5567	0.4406	0.6638
No log	2.9104	390	0.3761	0.6542	0.3761	0.6133
No log	2.9254	392	0.4932	0.7180	0.4932	0.7023
No log	2.9403	394	0.6324	0.7138	0.6324	0.7953
No log	2.9552	396	0.5753	0.6843	0.5753	0.7585
No log	2.9701	398	0.6212	0.6846	0.6212	0.7882
No log	2.9851	400	0.5342	0.6759	0.5342	0.7309
No log	3.0	402	0.4734	0.6972	0.4734	0.6880
No log	3.0149	404	0.4535	0.6937	0.4535	0.6734
No log	3.0299	406	0.4176	0.7076	0.4176	0.6462
No log	3.0448	408	0.3632	0.6594	0.3632	0.6027
No log	3.0597	410	0.3703	0.6029	0.3703	0.6085
No log	3.0746	412	0.3684	0.6515	0.3684	0.6069
No log	3.0896	414	0.4348	0.7120	0.4348	0.6594
No log	3.1045	416	0.5878	0.7068	0.5878	0.7666
No log	3.1194	418	0.5912	0.7018	0.5912	0.7689
No log	3.1343	420	0.4226	0.7131	0.4226	0.6500
No log	3.1493	422	0.3867	0.6282	0.3867	0.6218
No log	3.1642	424	0.3885	0.6071	0.3885	0.6233
No log	3.1791	426	0.3936	0.7017	0.3936	0.6274
No log	3.1940	428	0.4327	0.7252	0.4327	0.6578
No log	3.2090	430	0.5145	0.7448	0.5145	0.7173
No log	3.2239	432	0.4753	0.7373	0.4753	0.6894
No log	3.2388	434	0.4190	0.7358	0.4190	0.6473
No log	3.2537	436	0.3753	0.6796	0.3753	0.6126
No log	3.2687	438	0.4064	0.7303	0.4064	0.6375
No log	3.2836	440	0.4973	0.7534	0.4973	0.7052
No log	3.2985	442	0.5971	0.7461	0.5971	0.7727
No log	3.3134	444	0.4462	0.7451	0.4462	0.6680
No log	3.3284	446	0.4232	0.7370	0.4232	0.6506
No log	3.3433	448	0.4462	0.7474	0.4462	0.6680
No log	3.3582	450	0.5026	0.7494	0.5026	0.7089
No log	3.3731	452	0.4813	0.7460	0.4813	0.6937
No log	3.3881	454	0.4089	0.7300	0.4089	0.6395
No log	3.4030	456	0.4312	0.7291	0.4312	0.6566
No log	3.4179	458	0.5304	0.7447	0.5304	0.7283
No log	3.4328	460	0.7126	0.7181	0.7126	0.8442
No log	3.4478	462	0.5610	0.7198	0.5610	0.7490
No log	3.4627	464	0.3854	0.6517	0.3854	0.6208
No log	3.4776	466	0.3770	0.6403	0.3770	0.6140
No log	3.4925	468	0.3833	0.6501	0.3833	0.6191
No log	3.5075	470	0.3753	0.6249	0.3753	0.6126
No log	3.5224	472	0.3836	0.6575	0.3836	0.6193
No log	3.5373	474	0.3968	0.6666	0.3968	0.6299
No log	3.5522	476	0.4610	0.7057	0.4610	0.6789
No log	3.5672	478	0.4321	0.7028	0.4321	0.6573
No log	3.5821	480	0.3800	0.6544	0.3800	0.6164
No log	3.5970	482	0.3968	0.6882	0.3968	0.6299
No log	3.6119	484	0.4305	0.6972	0.4305	0.6561
No log	3.6269	486	0.4707	0.7170	0.4707	0.6861
No log	3.6418	488	0.5214	0.7179	0.5214	0.7221
No log	3.6567	490	0.4382	0.7109	0.4382	0.6620
No log	3.6716	492	0.4126	0.7105	0.4126	0.6423
No log	3.6866	494	0.4528	0.7253	0.4528	0.6729
No log	3.7015	496	0.3836	0.6819	0.3836	0.6194
No log	3.7164	498	0.3781	0.6713	0.3781	0.6149
0.6474	3.7313	500	0.4215	0.7153	0.4215	0.6492
0.6474	3.7463	502	0.6073	0.7437	0.6073	0.7793
0.6474	3.7612	504	0.6388	0.7402	0.6388	0.7992
0.6474	3.7761	506	0.5847	0.7417	0.5847	0.7647
0.6474	3.7910	508	0.4503	0.7353	0.4503	0.6711
0.6474	3.8060	510	0.3874	0.6815	0.3874	0.6224
0.6474	3.8209	512	0.4202	0.7194	0.4202	0.6482
0.6474	3.8358	514	0.4399	0.7281	0.4399	0.6633
0.6474	3.8507	516	0.3844	0.6692	0.3844	0.6200
0.6474	3.8657	518	0.4161	0.5757	0.4161	0.6451
0.6474	3.8806	520	0.3908	0.6204	0.3908	0.6252
0.6474	3.8955	522	0.4025	0.7023	0.4025	0.6344
0.6474	3.9104	524	0.4419	0.7280	0.4419	0.6648
0.6474	3.9254	526	0.5433	0.7469	0.5433	0.7371
0.6474	3.9403	528	0.5476	0.7441	0.5476	0.7400
0.6474	3.9552	530	0.3940	0.6945	0.3940	0.6277
0.6474	3.9701	532	0.3635	0.6672	0.3635	0.6029
0.6474	3.9851	534	0.3630	0.6303	0.3630	0.6025
0.6474	4.0	536	0.3863	0.6850	0.3863	0.6216
0.6474	4.0149	538	0.4110	0.7053	0.4110	0.6411

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1